Research map / Label-efficient and robust learning / Semi-supervised learning
What the Role is vs. What Plays the Role: Semi-Supervised Event Argument Extraction via Dual Question Answering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DualQA instead of the strongest baseline, PLMEE* | Event argument extraction · ACE 2005 | F1: 41.6 -> 45.4 | Helped |
| Use DualQA instead of the strongest baseline, PLMEE* | Event argument extraction · FewFC | F1: 40.2 -> 43.1 | Helped |
| Use question-answering EAR instead of sequence-labeling BERT-EE (ablation) | Event argument extraction · ACE 2005 | F1: 31.4 -> 37.5 | Helped |
| Use question-answering EAR instead of sequence-labeling BERT-EE (ablation) | Event argument extraction · FewFC | F1: 24.8 -> 32.0 | Helped |
| Add ERR as a dual task to EAR (ablation) | DualQA · ACE 2005 | F1: 37.5 -> 41.4 | Helped |
| Add ERR as a dual task to EAR (ablation) | DualQA · FewFC | F1: 32.0 -> 41.5 | Helped |
| Add iterative dual annotation of unlabeled data (ablation) | Joint-EAR-ERR · ACE 2005 | F1: 41.4 -> 45.4 | Helped |
| Add iterative dual annotation of unlabeled data (ablation) | Joint-EAR-ERR · FewFC | F1: 41.5 -> 43.1 | Helped |
| Add self-training to PLMEE | PLMEE · ACE 2005 | F1: 40.9 -> 41.6 | Helped |
| Add self-training to PLMEE | PLMEE · FewFC | F1: 38.8 -> 40.2 | Helped |
| Add self-training to EAR (ablation) | EAR · ACE 2005 | F1: 37.5 -> 39.3 | Helped |
| Add self-training to EAR (ablation) | EAR · FewFC | F1: 32.0 -> 34.4 | Helped |
Closest papers by meaning
- RoSE: A Role Correlation Structure-Enhanced Model for Multi-Event Argument Extraction (AAAI 2026 · similarity 0.89)
- MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations (NeurIPS 2024 · similarity 0.85)
- A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction (AAAI 2024 · similarity 0.83)
- Logic Induced High-Order Reasoning Network for Event-Event Relation Extraction (AAAI 2025 · similarity 0.82)
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.82)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.